Geekbench ML Score

283
Core ML CPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date October 09 2024 12:58 PM
Views 1

System Information

System Information
Operating System iOS 16.7.10
Model iPad Pro (12.9-inch)
Model IDiPad6,8
Motherboard J99aAP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 GHz
Cluster 12 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 3.90 GB
Inference Information
Framework Core ML
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 147
27.5 IPS
 
Image Classification (F16)
100% 130
24.3 IPS
 
Image Classification (I8)
99% 129
24.2 IPS
 
Image Segmentation (F32)
100% 123
2.06 IPS
 
Image Segmentation (F16)
100% 123
2.06 IPS
 
Image Segmentation (I8)
100% 123
2.06 IPS
 
Pose Estimation (F32)
100% 866
1.05 IPS
 
Pose Estimation (F16)
100% 859
1.04 IPS
 
Pose Estimation (I8)
100% 865
1.05 IPS
 
Object Detection (F32)
100% 161
12.0 IPS
 
Object Detection (F16)
100% 144
10.7 IPS
 
Object Detection (I8)
97% 160
12.0 IPS
 
Face Detection (F32)
100% 313
3.72 IPS
 
Face Detection (F16)
100% 310
3.68 IPS
 
Face Detection (I8)
99% 308
3.67 IPS
 
Depth Estimation (F32)
100% 411
3.18 IPS
 
Depth Estimation (F16)
100% 382
2.97 IPS
 
Depth Estimation (I8)
99% 382
2.96 IPS
 
Style Transfer (F32)
100% 1322
1.74 IPS
 
Style Transfer (F16)
100% 1321
1.74 IPS
 
Style Transfer (I8)
100% 1319
1.74 IPS
 
Image Super-Resolution (F32)
100% 373
13.3 IPS
 
Image Super-Resolution (F16)
100% 369
13.2 IPS
 
Image Super-Resolution (I8)
100% 366
13.1 IPS
 
Text Classification (F32)
100% 138
198.8 IPS
 
Text Classification (F16)
100% 115
165.6 IPS
 
Text Classification (I8)
96% 115
165.6 IPS
 
Machine Translation (F32)
100% 222
4.08 IPS
 
Machine Translation (F16)
100% 187
3.44 IPS
 
Machine Translation (I8)
99% 223
4.10 IPS
 

Compare

Set Baseline Geekbench 6 now available